This notebook builds an image classifier using Tensorflow 2.x and Tensorflow Hub.
Idenify a image of a dog given an image of a dog.
We are using the data from kaggle's dog breed identification competition.
Evaluation is a file with prediction probabilities for each dog breed of each test image.
Some information about the data are :-
- We are dealing with images (unstructured data) so its probabily best we use deep learning/transfer learning.
- There are 120 different breeds of dog (this means there are 120 different classes)
- There are 10,000+ images in training sets. (these images have labels)
- There are around 10,000+ images in the test set. (these images will have no label because we will want to predict them)